EP3185177A1 - Procédé et système de détection automatique de protocole d'acquisition d'images médicales - Google Patents

Procédé et système de détection automatique de protocole d'acquisition d'images médicales Download PDF

Info

Publication number
EP3185177A1
EP3185177A1 EP16205349.0A EP16205349A EP3185177A1 EP 3185177 A1 EP3185177 A1 EP 3185177A1 EP 16205349 A EP16205349 A EP 16205349A EP 3185177 A1 EP3185177 A1 EP 3185177A1
Authority
EP
European Patent Office
Prior art keywords
protocol
medical
medical images
image
image acquisition
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Withdrawn
Application number
EP16205349.0A
Other languages
German (de)
English (en)
Inventor
Parmeet Singh Bhatia
Amit Kale
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Siemens AG
Original Assignee
Siemens AG
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Siemens AG filed Critical Siemens AG
Publication of EP3185177A1 publication Critical patent/EP3185177A1/fr
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35—Clustering; Classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/51—Indexing; Data structures therefor; Storage structures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10072—Tomographic images
    • G06T2207/10088—Magnetic resonance imaging [MRI]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30204—Marker
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2210/00—Indexing scheme for image generation or computer graphics
    • G06T2210/41—Medical
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
    • G06V10/467—Encoded features or binary features, e.g. local binary patterns [LBP]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/03—Recognition of patterns in medical or anatomical images
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems

Definitions

  • This invention relates to a method and system for automatic detection of medical imaging acquisition protocol using image analytics and machine learning.
  • PACS Picture Archiving and Communication System
  • CT ultrasound computerized tomography
  • MR magnetic resonance
  • NM nuclear medicine
  • PET positron emission computed tomography
  • PACS Picture Archiving and Communication System
  • the PACS system includes an interface, which is a software application, which aids in accessing and retrieval of images stored in the PACS database. The queries received for a set of images are matched by means of DICOM header of the images stored in the PACS.
  • DICOM Digital Imaging and Communication in Medicine
  • NEMA National Electrical Manufacturers Association
  • the DICOM format consists of a header portion and an image data portion.
  • DICOM format uses a series of pre-defined tags, and allows the definition of new tags, which may or may not be present for a given dataset. This flexibility is one of the features that made the DICOM format so popular for medical imaging. Nevertheless, this popularity had led to the multiplication of tag definitions, and consequently, it is sometimes difficult to know which tags are used, and what they mean, making the extraction of header information more difficult.
  • DICOM tags include meta information which provide information associated with the medical image such as, details of the patient, the modality manufacturer, clinical findings and the like.
  • the DICOM tags may also contain the image acquisition protocol. Sometimes, the DICOM header does not contain the image acquisition protocol as it is an optional tag.
  • the method and device makes use of image analysis and statistical algorithms for automatically detecting the image acquisition protocol of a medical image.
  • the object of the invention is achieved by providing a method of automatically detecting medical imaging protocol.
  • the method includes determining, by a processor, anatomy under consideration from a set of Magnetic Resonance (MR) images using landmark detection algorithms. Further, the method includes automatically identifying image acquisition protocol associated with the set of medical images based on the determined anatomy. Further, medical images acquired with the identified image acquisition protocol are identified at different time instances from a medical image database. Finally, a comparative view of the medical images is provided on a display unit for analysis.
  • MR Magnetic Resonance
  • step of automatically identifying protocol associated with acquisition of the set of medical images based on the determined anatomy includes determining at least one feature associated with the medical images which characterize the acquisition protocol. Further, the medical images are assigned with an image acquisition protocol label, wherein the acquisition protocol label is assigned based on a classification of the medical images.
  • classifying the medical images includes detecting an outlier image acquisition protocol based on the at least one feature. Thereafter, the medical images are classified into at least one image acquisition protocol based on the features.
  • the identified image acquisition protocol of the set of MEDICAL images is displayed on the display unit.
  • a plurality of set of medical images of similar image acquisition protocols is displayed adjacent to one another.
  • the method of automatically identifying protocol associated with acquisition of the set of medical images based on the determined anatomy includes determining at least one feature associated with the medical images which characterize the acquisition protocol. Further, the medical images are classified based in the at least one feature. Thereafter, the MEDICAL images are assigned with an acquisition protocol label based on the classification of the MEDICAL images.
  • the feature comprises a two dimensional Local Binary Pattern (LBP), a 3 dimensional LBP and saliency weighted Histogram of the LBP.
  • LBP Local Binary Pattern
  • the method of classifying the medical images includes detecting an outlier image acquisition protocol based on the at least one feature. Further, the medical images are classified into at least one image acquisition protocol based on the features.
  • the method of detecting the outlier image acquisition protocol includes determining an error value associated with the features of the medical image. Further, the error value is compared against a threshold value to determine if the image acquisition protocol is an outlier. Thereafter, a result which indicates the image acquisition protocol of the medical image is an outlier is displayed.
  • classification of the medical images is performed using at least one of a probabilistic and a non-probabilistic classifier.
  • the outlier detection is performed using statistical transformation algorithms.
  • Another object of the invention is to provide a device to automatically detect the image acquisition protocol of a set of medical images.
  • the device includes a processor and a memory which includes processor executable instructions configured for automatically detecting an image acquisition protocol of a medical image.
  • FIG 1 illustrates a computing device for evaluating medical imaging devices, in accordance with an embodiment.
  • FIG 1 illustrates an exemplary block diagram 1 of the computing device 2 for generating electronic medical records, in accordance with an embodiment.
  • the computing device 2 includes a processor 4, a memory 6, a storage unit 14, an input/output (I/O) unit 18 and a communication module 20.
  • the computing device 2 is also communicatively coupled to a medical imaging device 22.
  • the medical imaging device 22 may include, but is not limited to, a Magnetic Resonance Imaging device, a Computerized Tomography imaging device and the like.
  • the aforementioned components are connected to each other by a bus unit 21.
  • the processor 4 means any type of computational circuit, such as, but not limited to, a microprocessor, a microcontroller, a complex instruction set computing microprocessor, a reduced instruction set computing microprocessor, a very long instruction word microprocessor, an explicitly parallel instruction computing microprocessor, a graphics processor, a digital signal processor, or any other type of processing circuit.
  • the processor 4 may also include embedded controllers, such as generic or programmable logic devices or arrays, application specific integrated circuits, single-chip computers, and the like.
  • the memory 6 may be volatile memory and non-volatile memory. A variety of computer-readable storage media may be stored in and accessed from the memory 6.
  • the memory 6 may include any suitable elements for storing data and machine-readable instructions, such as read only memory, random access memory, erasable programmable read only memory, electrically erasable programmable read only memory, hard drive, removable media drive for handling compact disks, digital video disks, diskettes, magnetic tape cartridges, memory cards, and the like.
  • the memory 6 includes one or more modules for generating medical reports with pre-defined protocol names, according to one or more embodiments described above.
  • the memory 6 includes an anatomy detection module 8, a feature extraction module 9, a statistical classifier module 10, an outlier protocol detection module 11 and label assignment module 12.
  • the anatomy detection module 8 is includes computer readable instructions for identifying an anatomy of human body part, in the medical image, using landmark detection algorithms, for example, ALPHA.
  • the medical image may include one or more slices of an anatomy of a subject as captured by a CT or MR modality.
  • the feature extraction module 9 is configured for extracting one or more features from the set of medical images.
  • the features that are extracted may be, for example, 2 dimensional Local Binary Patterns (2D LBP), 3 dimensional Local Binary Patterns (3D LBP) and Histogram of saliency weighted local binary (HSWLBP) patterns.
  • 2D LBP 2 dimensional Local Binary Patterns
  • 3D LBP 3 dimensional Local Binary Patterns
  • HSWLBP Histogram of saliency weighted local binary
  • the feature extraction module 9 may extract any other features such as, but not limited to filter based features from the medical images.
  • the features may be computed by determining a salient region in a volume of the medical image. Further, the salient regions in the volume of the medical image may be determined by applying a blurring filter and then assigning a saliency value for the pixels which are above a mean intensity value. In this manner, a very low intensity pixel is assigned a high saliency value which highlights the salient regions in the medical image.
  • the Local binary patterns are computed by known methods for a particular radius and sample size. For example, the LBP may be computed for a radius of 1 and sample size 8.
  • the features extraction module 9 is configured to extract histogram of saliency weighted lower binary patterns (HSWLBP).
  • the HSWLBP is computed by developing a 256 dimensional histogram of the combined LBP of all the slices of an anatomy. The aforementioned features are used to classify the medical images into an image acquisition protocol from a group of several image acquisition protocols.
  • the memory 6 includes the outlier protocol detection module 11, which is configured to detect if the medical image does not belong to a set of known image acquisition protocols.
  • the outlier protocol detection module 11 determines if the medical image is of an outlier protocol by using a novelty detection algorithm. Initially, an error value associated with the medical image in the context of a reconstruction of the medical image in one of the known set of protocols is determined. In case the error is greater than a threshold value, then the image acquisition protocol of the medical image is concluded to be an outlier protocol. In other words, the image acquisition protocol of the medical image does not belong to the known set of image acquisition protocol.
  • the memory 6 includes the statistical classifier module 10, which classifies the medical image into one of the image acquisition protocol from a group of image acquisition protocol.
  • the statistical classifier module 10 may determine the image acquisition protocol of the medical image based on the features extracted by the feature extraction module 9.
  • the statistical classifier module 10 may be configured to perform the classification by using machine learning algorithms such as random forests and support vector machines. Further, the statistical classifier module 10 may be trained using existing medical images of the known protocol set.
  • the storage unit 14 may be a non-transitory storage medium configured for storing medical image data 16 which includes medical images acquired in various imaging protocols.
  • the images data 16 in the storage unit may be used to train the statistical classifier module 10.
  • the input output module 18 may include a keyboard, keypad, touch sensitive display screen, mouse and the like.
  • the input /output devices 18 enable the user to interact with the device 2 for controlling the operating state.
  • a display unit may display a screen which includes one or more graphical objects indicating the image acquisition protocol of the medical image which is considered for analysis.
  • the device 2 further includes a communication module 20 for communicating with other devices via a network connection.
  • the communication module 20 may include a Wi-Fi transceiver, a network interface card (NIC) and the like.
  • FIG 2 illustrates an exemplary block diagram of the working of the feature extraction module 9, in accordance with an embodiment.
  • the feature extraction module 9 receives a medical image from a source.
  • the source of the medical image may be the image data 16 which is stored in the storage unit 14.
  • the medical image 32 may be acquired directly from the imaging modality 22.
  • the feature extraction module 9 is configured to extract one or more features (F 1 , F 2 ... F N ) from the medical image 32.
  • the features may include 2 dimensional and 3 dimensional lower binary patters (LBPs).
  • the features (F 1 , F 2 ... F N ) include Histogram of Saliency Weighted LBPs (HSWLBP).
  • the 2D and 3D LBPs may be determined by the feature extraction module 9 by using known algorithms for determining LBPs of images.
  • a Gaussian filter is applied to a volume in the medical image 32 using 3D Gaussian kernel with variance equal to one. Thereafter, all the voxels in blurred version of volume are assigned saliency of 1 if the intensity value of the voxels are above mean intensity value of the whole volume and 0 otherwise.
  • the features computed by the feature extraction module 9 are used to determine the image acquisition protocol of the medical image 32. Further, the feature extraction module 9 may be capable of extracting any other feature which helps in the determination of the image acquisition protocol. Further the features generated by the feature extraction module 9 are passed on to the statistical classifier module 11 and the outlier protocol detection module 10.
  • the outlier protocol detection module 10 is configured to process the features (F 1 , F 2 ... F N ) to determine if the medical image 32 is generated using an unknown protocol.
  • the outlier protocol detection module 10 may be configured to implement a novelty detection algorithm for determining an outlier protocol.
  • the outlier protocol detection module 10 may make use of a Kernel-Principle Component Analysis (PCA) algorithm for determining an error value associated with the reconstruction of the features of the medical image in a known feature space. In case the error value exceeds a threshold value then the image acquisition protocol used for acquiring the medical image 32 is determined to be an outlier.
  • PCA Kernel-Principle Component Analysis
  • the reconstruction error will be low and vice-versa.
  • a threshold may be determined empirically to classify the sample as an outlier, for which the reconstruction error is above the threshold. In case the outlier protocol detection module 10 determines that the protocol used for acquiring the medical image 32 is an outlier protocol the medical image 32 is discarded and there is no further processing of the same.
  • the statistical classifier module 11 processes the features (F 1 , F 2 ... F N ) which characterize different image acquisition protocols.
  • the features (F 1 , F 2 ... F N ) are selected such that the classes of image acquisition protocols are linearly separable.
  • the statistical classifier module 11 may be configured to Support Vector Machine (SVM) algorithm with linear kernel to provide a good classification of the imaging protocols. Further, the statistical classifier module 11 may make use of other classification algorithms such as Random Forests for classification of the imaging protocols. Furthermore, the statistical classifier module 11 may be trained using a training image data for learning the characteristics of the features of different imaging protocols.
  • SVM Support Vector Machine
  • FIG 3 illustrates a flowchart 50 of exemplary method steps involved automatically detecting the image acquisition protocol, in accordance with one or more embodiments.
  • anatomy of a medical image is detected.
  • the anatomy may be detected using landmark detection algorithms such as, but not limited to, ALPHA.
  • an image acquisition protocol associated with acquisition of the set of medical images is determined based on the anatomy.
  • the method of automatically identifying protocol associated with acquisition of the set of medical images based on the determined anatomy includes determining at least one feature associated with the medical images which characterize the acquisition protocol.
  • the feature comprises a two dimensional Local Binary Pattern (LBP), a 3 dimensional LBP and saliency weighted Histogram of the LBP.
  • LBP Local Binary Pattern
  • the method of classifying the medical images includes detecting an outlier image acquisition protocol based on the at least one feature. Further, the medical images are classified into at least one image acquisition protocol based on the features. In some embodiments, the method of detecting the outlier image acquisition protocol includes determining an error value associated with the features of the medical image. Further, the error value is compared against a threshold value to determine if the image acquisition protocol is an outlier. Thereafter, a result which indicates the image acquisition protocol of the medical image is an outlier is displayed. In some other embodiments, the outlier detection is performed using statistical transformation algorithms.
  • the medical images are classified based in the at least one feature. Thereafter, the medical images are assigned with an acquisition protocol label based on the classification of the medical images.
  • classification of the medical images is performed using at least one of a probabilistic and a non-probabilistic classifier algorithm.
  • images acquired with the identified protocol at different time instances from a medical image database are labelled and displayed.
  • a plurality of medical images of similar image acquisition protocols is displayed adjacent to one another.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Library & Information Science (AREA)
  • Health & Medical Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Radiology & Medical Imaging (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Epidemiology (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Primary Health Care (AREA)
  • Public Health (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Quality & Reliability (AREA)
  • Software Systems (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)
  • Image Analysis (AREA)
EP16205349.0A 2015-12-24 2016-12-20 Procédé et système de détection automatique de protocole d'acquisition d'images médicales Withdrawn EP3185177A1 (fr)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
IN1336KO2015 2015-12-24

Publications (1)

Publication Number Publication Date
EP3185177A1 true EP3185177A1 (fr) 2017-06-28

Family

ID=57860614

Family Applications (1)

Application Number Title Priority Date Filing Date
EP16205349.0A Withdrawn EP3185177A1 (fr) 2015-12-24 2016-12-20 Procédé et système de détection automatique de protocole d'acquisition d'images médicales

Country Status (3)

Country Link
US (1) US10698981B2 (fr)
EP (1) EP3185177A1 (fr)
CN (1) CN107016032A (fr)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3185177A1 (fr) * 2015-12-24 2017-06-28 Siemens Aktiengesellschaft Procédé et système de détection automatique de protocole d'acquisition d'images médicales
US10878561B2 (en) 2018-05-31 2020-12-29 General Electric Company Automated scanning workflow
US20220249168A1 (en) * 2019-06-28 2022-08-11 Formus Labs Limited Orthopaedic pre-operative planning system
US11961606B2 (en) * 2019-11-26 2024-04-16 Blackford Analysis Ltd. Systems and methods for processing medical images for in-progress studies
CN111755118B (zh) * 2020-03-16 2024-03-08 腾讯科技（深圳）有限公司 医疗信息处理方法、装置、电子设备及存储介质
US20230377719A1 (en) * 2022-05-20 2023-11-23 Blackford Analysis Ltd. Systems and Methods for Routing Medical Images Using Order Data
CN115834453B (zh) * 2023-02-14 2023-06-02 浙江德塔森特数据技术有限公司 手持协议检测终端的协议检测方法和手持协议检测终端

Family Cites Families (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001094720A (ja) * 1999-09-27 2001-04-06 Fuji Photo Film Co Ltd 画像出力処理装置および画像出力処理方法
US7072498B1 (en) * 2001-11-21 2006-07-04 R2 Technology, Inc. Method and apparatus for expanding the use of existing computer-aided detection code
EP1665113A2 (fr) * 2003-09-17 2006-06-07 Koninklijke Philips Electronics N.V. Comptes rendus d'examen repetes
US20060008130A1 (en) * 2004-06-29 2006-01-12 Youji Yamamichi Medical image output system, apparatus and method
JP2006006790A (ja) 2004-06-29 2006-01-12 Konica Minolta Medical & Graphic Inc 医用画像出力システム及び医用画像出力方法
JP2008006191A (ja) * 2006-06-30 2008-01-17 Fujifilm Corp 画像処理装置
JP4979334B2 (ja) * 2006-10-18 2012-07-18 富士フイルム株式会社 医用画像読影支援システム及びプログラム
JP4976164B2 (ja) * 2007-03-02 2012-07-18 富士フイルム株式会社 類似症例検索装置、方法、およびプログラム
US20090287505A1 (en) * 2008-05-14 2009-11-19 Wood Christopher H Systems and methods for efficient computer-aided analysis of medical information
CN101295309B (zh) 2008-05-22 2011-05-04 江苏大学 一种医学图像识别的方法
US8588555B1 (en) 2009-06-12 2013-11-19 Cognitive Electronics, Inc. Power-efficient sensory recognition processor
US9712498B2 (en) * 2009-10-14 2017-07-18 Trice Imaging, Inc. Systems and devices for encrypting, converting and interacting with medical images
US8897532B2 (en) 2012-07-11 2014-11-25 General Electric Company Systems and methods for performing image type recognition
US20140222444A1 (en) * 2013-02-04 2014-08-07 Dixit S.R.L. Method And System For Clinical Trial Management
US9715576B2 (en) * 2013-03-15 2017-07-25 II Robert G. Hayter Method for searching a text (or alphanumeric string) database, restructuring and parsing text data (or alphanumeric string), creation/application of a natural language processing engine, and the creation/application of an automated analyzer for the creation of medical reports
CN103473569A (zh) 2013-09-22 2013-12-25 江苏美伦影像系统有限公司 基于svm的医学影像分类方法
US9626476B2 (en) * 2014-03-27 2017-04-18 Change Healthcare Llc Apparatus, method and computer-readable storage medium for transforming digital images
EP3185177A1 (fr) * 2015-12-24 2017-06-28 Siemens Aktiengesellschaft Procédé et système de détection automatique de protocole d'acquisition d'images médicales

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
"ImageCLEF Experimental Evaluation in Visual Information Retrieval", 1 January 2010, SPRINGER, article HENNING MULLER: "ImageCLEF Experimental Evaluation in Visual Information Retrieval", pages: 403 - 405, XP055371839 *
ALEX BUI: "Medical Imaging Informatics", 1 January 2010, SPRINGER, pages: 252 - 255, XP055371816 *
ALEXIA BRIASSOULI: "Health Monitoring and Personalized Feedback using Multimedia Data", 1 January 2015, SPRINGER, article ALEXIA BRIASSOULI, pages: 74 - 91, XP055371834 *
GEORGE C. KAGADIS: "Informatics in Medical Imaging", 1 January 2012, CRC, pages: 258, XP055371821 *

Also Published As

Publication number Publication date
CN107016032A (zh) 2017-08-04
US20170185713A1 (en) 2017-06-29
US10698981B2 (en) 2020-06-30

Similar Documents

Publication Publication Date Title
US10698981B2 (en) Automatic detection of medical image acquisition protocol
Yao et al. Weakly supervised medical diagnosis and localization from multiple resolutions
Antropova et al. A deep feature fusion methodology for breast cancer diagnosis demonstrated on three imaging modality datasets
Srinivas et al. Content based medical image retrieval using dictionary learning
US10176580B2 (en) Diagnostic system and diagnostic method
Avni et al. X-ray categorization and retrieval on the organ and pathology level, using patch-based visual words
EP2888686B1 (fr) Détection et récupération automatiques d'annotations antérieures pertinentes pour une étude d'imagerie en vue d'une visualisation et d'un établissement de rapport d'une grande efficacité
US8031917B2 (en) System and method for smart display of CAD markers
CN106796621B (zh) 图像报告注释识别
CN108172275B (zh) 一种医学影像处理方法及装置
CN110853739B (zh) 图像管理显示方法、装置、计算机设备及存储介质
US20190035075A1 (en) Method and apparatus for classifying a data point in imaging data
Gaonkar et al. Quantitative analysis of neural foramina in the lumbar spine: an imaging informatics and machine learning study
CN112102235B (zh) 人体部位识别方法、计算机设备和存储介质
US9538920B2 (en) Standalone annotations of axial-view spine images
US20220285011A1 (en) Document creation support apparatus, document creation support method, and program
France et al. Classification and retrieval of thoracic diseases using patch-based visual words: a study on chest x-rays
Ghantasala et al. Identification of Normal and Abnormal Mammographic Images Using Deep Neural Network
US10803593B2 (en) Method and system for image compression
Wang et al. Preparing CT imaging datasets for deep learning in lung nodule analysis: Insights from four well-known datasets
US11301720B2 (en) Training set enrichment with insignificantly-abnormal medical images
Murugan et al. Efficient clustering of unlabeled brain DICOM images based on similarity
Li et al. Tbidoc: 3d content-based ct image retrieval system for traumatic brain injury
Okuyar et al. Ischemia and Hemorrhage detection in CT images with Hyper parameter optimization of classification models and Improved UNet Segmentation Model
JP2021105960A (ja) 医用情報処理装置

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE

17P Request for examination filed

Effective date: 20161220

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

AX Request for extension of the european patent

Extension state: BA ME

RAP1 Party data changed (applicant data changed or rights of an application transferred)

Owner name: SIEMENS AKTIENGESELLSCHAFT

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN

18D Application deemed to be withdrawn

Effective date: 20180103